A Novel Approach for Classifying Medical Images Using Data Mining Techniques

The ever increasing amounts of patient data in the form of medical images, imposes new challenges to clinical routine such as diagnosis, treatment and monitoring. Hence research in medical data mining is the state of the art. In this paper, a novel approach for automatic classification of fundus images is proposed. The method uses image and data pre-processing techniques to improve the performance of machine learning classifiers. Further a discretization method is proposed to improve the accuracy of the classifiers. Experiments were done on retinal fundus images using the proposed method on three classifiers Naïve Bayes NB, k nearest neighbor kNN, and support vector machine SVM. Results in terms of classification accuracy and area under the Roc curve AUC show that NB outperform the other classifiers as per the proposed method. Keywords— Medical image mining, feature selection, discretization, NB, kNN, SVM, AUC .